Magnetic resonance imaging (MRI) has greatly advanced neuroscience research and clinical diagnostics. However, imaging data collected across different scanners, acquisition protocols, or imaging sites often exhibit substantial heterogeneity, known as "batch effects" or "site effects." These non-biological sources of variability can obscure true biological signals, reduce reproducibility and statistical power, and severely impair the generalizability of learning-based models across datasets. Image harmonization is grounded in the central hypothesis that site-related biases can be eliminated or mitigated while preserving meaningful biological information, thereby improving data comparability and consistency. This review provides a comprehensive overview of key concepts, methodological advances, publicly available datasets, and evaluation metrics in the field of MRI harmonization. We systematically cover the full imaging pipeline and categorize harmonization approaches into prospective acquisition and reconstruction, retrospective image-level and feature-level methods, and traveling-subject-based techniques. By synthesizing existing methods and evidence, we revisit the central hypothesis of image harmonization and show that, although site invariance can be achieved with current techniques, further evaluation is required to verify the preservation of biological information. To this end, we summarize the remaining challenges and highlight key directions for future research, including the need for standardized validation benchmarks, improved evaluation strategies, and tighter integration of harmonization methods across the imaging pipeline.

Diffusion-weighted MRI (dMRI) is increasingly used to study the normal and abnormal development of fetal brain in-utero. It offers invaluable insights into the neurodevelopmental processes in the fetal stage. However, reliable analysis of fetal dMRI data requires dedicated computational methods that are currently unavailable. The lack of automated methods for fast, accurate, and reproducible data analysis has seriously limited our ability to tap the potential of fetal brain dMRI for medical and scientific applications. In this work, we developed and validated a unified computational framework to:1) segment the brain tissue into white matter, cortical/subcortical gray matter, and cerebrospinal fluid,:2) segment 31 distinct white matter tracts, and:3) parcellate the brain's cortex, deep gray nuclei, and white matter structures into 96 anatomically meaningful regions. We utilized a set of manual, semi-automatic, and automatic approaches to annotate 97 fetal brains. Using these labels, we developed and validated a multi-task deep learning method to perform the three computations. Evaluations show that the new method can accurately carry out all three tasks, achieving a mean Dice similarity coefficient of 0.865 on tissue segmentation, 0.825 on white matter tract segmentation, and 0.819 on parcellation. Further validation on independent external data shows generalizability of the proposed method. The new method can help advance the field of fetal neuroimaging as it can lead to substantial improvements in fetal brain tractography, tract-specific analysis, and structural connectivity assessment.

• Training supervised on synthetic data effectively leverages spatial information. • Transformers showed faster convergence and better accuracy than CNN-based networks. • Larger receptive fields yielded improved estimator performance. • Neighborhood-attention permitted larger receptive fields than self-attention. • Novel fractal-noise maps enabled quantitative assessment of estimator performance. In medical image analysis, the utilization of biophysical models for signal analysis offers valuable insights into the underlying tissue types and microstructural processes. In diffusion-weighted magnetic resonance imaging (DWI), a major challenge lies in accurately estimating model parameters from the acquired data due to the inherently low signal-to-noise ratio (SNR) of the signal measurements and the complexity of solving the ill-posed inverse problem. Conventional model fitting approaches treat individual voxels as independent. However, the tissue microenvironment is typically homogeneous in a local environment, where neighboring voxels may contain correlated information. To harness the potential benefits of exploiting correlations among signals in adjacent voxels, this study introduces a novel approach to deep learning parameter estimation that effectively incorporates relevant spatial information. This is achieved by training neural networks on patches of synthetic data encompassing plausible combinations of direct correlations between neighboring voxels. We evaluated the approach on the intravoxel incoherent motion (IVIM) model in DWI. We explored the potential of several deep learning architectures to incorporate spatial information using self-supervised and supervised learning. We assessed performance quantitatively using novel fractal-noise-based synthetic data, which provide ground truths possessing spatial correlations. Additionally, we present results of the approach applied to in vivo DWI data consisting of twelve repetitions from a healthy volunteer. We demonstrate that supervised training on larger patch sizes using attention models leads to substantial performance improvements over both conventional voxelwise model fitting and convolution-based approaches.

In-utero fetal MRI is emerging as an important tool in the diagnosis and analysis of the developing human brain. Automatic segmentation of the developing fetal brain is a vital step in the quantitative analysis of prenatal neurodevelopment both in the research and clinical context. However, manual segmentation of cerebral structures is time-consuming and prone to error and inter-observer variability. Therefore, we organized the Fetal Tissue Annotation (FeTA) Challenge in 2021 in order to encourage the development of automatic segmentation algorithms on an international level. The challenge utilized FeTA Dataset, an open dataset of fetal brain MRI reconstructions segmented into seven different tissues (external cerebrospinal fluid, gray matter, white matter, ventricles, cerebellum, brainstem, deep gray matter). 20 international teams participated in this challenge, submitting a total of 21 algorithms for evaluation. In this paper, we provide a detailed analysis of the results from both a technical and clinical perspective. All participants relied on deep learning methods, mainly U-Nets, with some variability present in the network architecture, optimization, and image pre- and post-processing. The majority of teams used existing medical imaging deep learning frameworks. The main differences between the submissions were the fine tuning done during training, and the specific pre- and post-processing steps performed. The challenge results showed that almost all submissions performed similarly. Four of the top five teams used ensemble learning methods. However, one team's algorithm performed significantly superior to the other submissions, and consisted of an asymmetrical U-Net network architecture. This paper provides a first of its kind benchmark for future automatic multi-tissue segmentation algorithms for the developing human brain in utero.

Functional MRI (fMRI) is widely used to study the functional organization of normal and pathological brains. However, the fMRI signal may be contaminated by subject motion artifacts that are only partially mitigated by motion correction strategies. These artifacts lead to distance-dependent biases in the inferred signal correlations. To mitigate these spurious effects, motion-corrupted volumes are censored from fMRI time series. Censoring can result in discontinuities in the fMRI signal, which may lead to substantial alterations in functional connectivity analysis. We propose a new approach to recover the missing entries from censoring based on structured low rank matrix completion. We formulated the artifact-reduction problem as the recovery of a super-resolved matrix from unprocessed fMRI measurements. We enforced a low rank prior on a large structured matrix, formed from the samples of the time series, to recover the missing entries. The recovered time series, in addition to being motion compensated, are also slice-time corrected at a fine temporal resolution. To achieve a fast and memory-efficient solution for our proposed optimization problem, we employed a variable splitting strategy. We validated the algorithm with simulations, data acquired under different motion conditions, and datasets from the ABCD study. Functional connectivity analysis showed that the proposed reconstruction resulted in connectivity matrices with lower errors in pair-wise correlation than non-censored and censored time series based on a standard processing pipeline. In addition, seed-based correlation analyses showed improved delineation of the default mode network. These demonstrate that the method can effectively reduce the adverse effects of motion in fMRI analysis.

The interpretation and analysis of Magnetic resonance imaging (MRI) benefit from high spatial resolution. Unfortunately, direct acquisition of high spatial resolution MRI is time-consuming and costly, which increases the potential for motion artifact, and suffers from reduced signal-to-noise ratio (SNR). Super-resolution reconstruction (SRR) is one of the most widely used methods in MRI since it allows for the trade-off between high spatial resolution, high SNR, and reduced scan times. Deep learning has emerged for improved SRR as compared to conventional methods. However, current deep learning-based SRR methods require large-scale training datasets of high-resolution images, which are practically difficult to obtain at a suitable SNR. We sought to develop a methodology that allows for dataset-free deep learning-based SRR, through which to construct images with higher spatial resolution and of higher SNR than can be practically obtained by direct Fourier encoding. We developed a dataset-free learning method that leverages a generative neural network trained for each specific scan or set of scans, which in turn, allows for SRR tailored to the individual patient. With the SRR from three short duration scans, we achieved high quality brain MRI at an isotropic spatial resolution of 0.125 cubic mm with six minutes of imaging time for T2 contrast and an average increase of 7.2 dB (34.2%) in SNR to these short duration scans. Motion compensation was achieved by aligning the three short duration scans together. We assessed our technique on simulated MRI data and clinical data acquired from 15 subjects. Extensive experimental results demonstrate that our approach achieved superior results to state-of-the-art methods, while in parallel, performed at reduced cost as scans delivered with direct high-resolution acquisition.

Lung cancer is by far the leading cause of cancer death in the US. Recent studies have demonstrated the effectiveness of screening using low dose CT (LDCT) in reducing lung cancer related mortality. While lung nodules are detected with a high rate of sensitivity, this exam has a low specificity rate and it is still difficult to separate benign and malignant lesions. The ISBI 2018 Lung Nodule Malignancy Prediction Challenge, developed by a team from the Quantitative Imaging Network of the National Cancer Institute, was focused on the prediction of lung nodule malignancy from two sequential LDCT screening exams using automated (non-manual) algorithms. We curated a cohort of 100 subjects who participated in the National Lung Screening Trial and had established pathological diagnoses. Data from 30 subjects were randomly selected for training and the remaining was used for testing. Participants were evaluated based on the area under the receiver operating characteristic curve (AUC) of nodule-wise malignancy scores generated by their algorithms on the test set. The challenge had 17 participants, with 11 teams submitting reports with method description, mandated by the challenge rules. Participants used quantitative methods, resulting in a reporting test AUC ranging from 0.698 to 0.913. The top five contestants used deep learning approaches, reporting an AUC between 0.87 - 0.91. The team's predictor did not achieve significant differences from each other nor from a volume change estimate (p =.05 with Bonferroni-Holm's correction).

Fetal cortical plate segmentation is essential in quantitative analysis of fetal brain maturation and cortical folding. Manual segmentation of the cortical plate, or manual refinement of automatic segmentations is tedious and time-consuming. Automatic segmentation of the cortical plate, on the other hand, is challenged by the relatively low resolution of the reconstructed fetal brain MRI scans compared to the thin structure of the cortical plate, partial voluming, and the wide range of variations in the morphology of the cortical plate as the brain matures during gestation. To reduce the burden of manual refinement of segmentations, we have developed a new and powerful deep learning segmentation method. Our method exploits new deep attentive modules with mixed kernel convolutions within a fully convolutional neural network architecture that utilizes deep supervision and residual connections. We evaluated our method quantitatively based on several performance measures and expert evaluations. Results show that our method outperforms several state-of-the-art deep models for segmentation, as well as a state-of-the-art multi-atlas segmentation technique. We achieved average Dice similarity coefficient of 0.87, average Hausdorff distance of 0.96 mm, and average symmetric surface difference of 0.28 mm on reconstructed fetal brain MRI scans of fetuses scanned in the gestational age range of 16 to 39 weeks (28.6± 5.3). With a computation time of less than 1 minute per fetal brain, our method can facilitate and accelerate large-scale studies on normal and altered fetal brain cortical maturation and folding.

Fetal magnetic resonance imaging (MRI) is challenged by uncontrollable, large, and irregular fetal movements. It is, therefore, performed through visual monitoring of fetal motion and repeated acquisitions to ensure diagnostic-quality images are acquired. Nevertheless, visual monitoring of fetal motion based on displayed slices, and navigation at the level of stacks-of-slices is inefficient. The current process is highly operator-dependent, increases scanner usage and cost, and significantly increases the length of fetal MRI scans which makes them hard to tolerate for pregnant women. To help build automatic MRI motion tracking and navigation systems to overcome the limitations of the current process and improve fetal imaging, we have developed a new real-time image-based motion tracking method based on deep learning that learns to predict fetal motion directly from acquired images. Our method is based on a recurrent neural network, composed of spatial and temporal encoder-decoders, that infers motion parameters from anatomical features extracted from sequences of acquired slices. We compared our trained network on held-out test sets (including data with different characteristics, e.g. different fetuses scanned at different ages, and motion trajectories recorded from volunteer subjects) with networks designed for estimation as well as methods adopted to make predictions. The results show that our method outperformed alternative techniques, and achieved real-time performance with average errors of 3.5 and 8 degrees for the estimation and prediction tasks, respectively. Our real-time deep predictive motion tracking technique can be used to assess fetal movements, to guide slice acquisitions, and to build navigation systems for fetal MRI.

High resolution (HR) magnetic resonance images (MRI) provide rich tissue anatomical information that enables accurate diagnostics and pathological analysis. However, the acquisition of HR MRI is limited by hardware restrictions, scanning time, and signal-to-noise ratio (SNR) in clinical applications. Recently, deep learning has shown promising power for improving the spatial resolution of MRI. In this study, we propose a multilevel and parallel Conv-Deconv super-resolution (CDSR) network to reconstruct high-quality HR MRI from low resolution (LR) inputs. Different from current SR methods based on convolutional neural networks (CNNs), we connect parallel 3D convolution and deconvolution filters to capture context information and extract multi-level features. Hierarchical features are adaptively upsampled using each of their following deconvolution layers and then fused together to recover the HR details. In order to alleviate the optimization difficulty, we introduce the interpolated input to the fused output, which performs like a cross-scale residual learning strategy, hence accelerates the convergence. Extensive experimental results on three benchmark datasets show that our proposed method outperforms current reported MRI SR methods and sets a new state-of-the-art performance.

With an aim to increase the capture range and accelerate the performance of state-of-the-art inter-subject and subject-to-template 3-D rigid registration, we propose deep learning-based methods that are trained to find the 3-D position of arbitrarily-oriented subjects or anatomy in a canonical space based on slices or volumes of medical images. For this, we propose regression convolutional neural networks (CNNs) that learn to predict the angle-axis representation of 3-D rotations and translations using image features. We use and compare mean square error and geodesic loss to train regression CNNs for 3-D pose estimation used in two different scenarios: slice-to-volume registration and volume-to-volume registration. As an exemplary application, we applied the proposed methods to register arbitrarily oriented reconstructed images of fetuses scanned in-utero at a wide gestational age range to a standard atlas space. Our results show that in such registration applications that are amendable to learning, the proposed deep learning methods with geodesic loss minimization achieved 3-D pose estimation with a wide capture range in real-time (<100ms). We also tested the generalization capability of the trained CNNs on an expanded age range and on images of newborn subjects with similar and different MR image contrasts. We trained our models on T2-weighted fetal brain MRI scans and used them to predict the 3-D pose of newborn brains based on T1-weighted MRI scans. We showed that the trained models generalized well for the new domain when we performed image contrast transfer through a conditional generative adversarial network. This indicates that the domain of application of the trained deep regression CNNs can be further expanded to image modalities and contrasts other than those used in training. A combination of our proposed methods with accelerated optimization-based registration algorithms can dramatically enhance the performance of automatic imaging devices and image processing methods of the future.

Deep convolutional neural networks (CNN) have recently achieved superior performance at the task of medical image segmentation compared to classic models. However, training a generalizable CNN requires a large amount of training data, which is difficult, expensive, and time-consuming to obtain in medical settings. Active Learning (AL) algorithms can facilitate training CNN models by proposing a small number of the most informative data samples to be annotated to achieve a rapid increase in performance. We proposed a new active learning method based on Fisher information (FI) for CNNs for the first time. Using efficient backpropagation methods for computing gradients together with a novel low-dimensional approximation of FI enabled us to compute FI for CNNs with a large number of parameters. We evaluated the proposed method for brain extraction with a patch-wise segmentation CNN model in two different learning scenarios: universal active learning and active semi-automatic segmentation. In both scenarios, an initial model was obtained using labeled training subjects of a source data set and the goal was to annotate a small subset of new samples to build a model that performs well on the target subject(s). The target data sets included images that differed from the source data by either age group (e.g. newborns with different image contrast) or underlying pathology that was not available in the source data. In comparison to several recently proposed AL methods and brain extraction baselines, the results showed that FI-based AL outperformed the competing methods in improving the performance of the model after labeling a very small portion of target data set (<0.25%).

In magnetic resonance (MR), hardware limitations, scan time constraints, and patient movement often result in the acquisition of anisotropic 3-D MR images with limited spatial resolution in the out-of-plane views. Our goal is to construct an isotropic high-resolution (HR) 3-D MR image through upsampling and fusion of orthogonal anisotropic input scans. We propose a multiframe super-resolution (SR) reconstruction technique based on sparse representation of MR images. Our proposed algorithm exploits the correspondence between the HR slices and the low-resolution (LR) sections of the orthogonal input scans as well as the self-similarity of each input scan to train pairs of overcomplete dictionaries that are used in a sparse-land local model to upsample the input scans. The upsampled images are then combined using wavelet fusion and error backprojection to reconstruct an image. Features are learned from the data and no extra training set is needed. Qualitative and quantitative analyses were conducted to evaluate the proposed algorithm using simulated and clinical MR scans. Experimental results show that the proposed algorithm achieves promising results in terms of peak signal-to-noise ratio, structural similarity image index, intensity profiles, and visualization of small structures obscured in the LR imaging process due to partial volume effects. Our novel SR algorithm outperforms the nonlocal means (NLM) method using self-similarity, NLM method using self-similarity and image prior, self-training dictionary learning-based SR method, averaging of upsampled scans, and the wavelet fusion method. Our SR algorithm can reduce through-plane partial volume artifact by combining multiple orthogonal MR scans, and thus can potentially improve medical image analysis, research, and clinical diagnosis.

Brain extraction or whole brain segmentation is an important first step in many of the neuroimage analysis pipelines. The accuracy and the robustness of brain extraction, therefore, are crucial for the accuracy of the entire brain analysis process. The state-of-the-art brain extraction techniques rely heavily on the accuracy of alignment or registration between brain atlases and query brain anatomy, and/or make assumptions about the image geometry, and therefore have limited success when these assumptions do not hold or image registration fails. With the aim of designing an accurate, learning-based, geometry-independent, and registration-free brain extraction tool, in this paper, we present a technique based on an auto-context convolutional neural network (CNN), in which intrinsic local and global image features are learned through 2-D patches of different window sizes. We consider two different architectures: 1) a voxelwise approach based on three parallel 2-D convolutional pathways for three different directions (axial, coronal, and sagittal) that implicitly learn 3-D image information without the need for computationally expensive 3-D convolutions and 2) a fully convolutional network based on the U-net architecture. Posterior probability maps generated by the networks are used iteratively as context information along with the original image patches to learn the local shape and connectedness of the brain to extract it from non-brain tissue. The brain extraction results we have obtained from our CNNs are superior to the recently reported results in the literature on two publicly available benchmark data sets, namely, LPBA40 and OASIS, in which we obtained the Dice overlap coefficients of 97.73% and 97.62%, respectively. Significant improvement was achieved via our auto-context algorithm. Furthermore, we evaluated the performance of our algorithm in the challenging problem of extracting arbitrarily oriented fetal brains in reconstructed fetal brain magnetic resonance imaging (MRI) data sets. In this application, our voxelwise auto-context CNN performed much better than the other methods (Dice coefficient: 95.97%), where the other methods performed poorly due to the non-standard orientation and geometry of the fetal brain in MRI. Through training, our method can provide accurate brain extraction in challenging applications. This, in turn, may reduce the problems associated with image registration in segmentation tasks.

Simultaneous multi-slice (SMS) echo-planar imaging has had a huge impact on the acceleration and routine use of diffusion-weighted MRI (DWI) in neuroimaging studies in particular the human connectome project; but also holds the potential to facilitate DWI of moving subjects, as proposed by the new technique developed in this paper. We present a novel registration-based motion tracking technique that takes advantage of the multi-plane coverage of the anatomy by simultaneously acquired slices to enable robust reconstruction of neural microstructure from SMS DWI of moving subjects. Our technique constitutes three main components: 1) motion tracking and estimation using SMS registration, 2) detection and rejection of intra-slice motion, and 3) robust reconstruction. Quantitative results from 14 volunteer subject experiments and the analysis of motion-corrupted SMS DWI of 6 children indicate robust reconstruction in the presence of continuous motion and the potential to extend the use of SMS DWI in very challenging populations.

In magnetic resonance (MR), hardware limitation, scanning time, and patient comfort often result in the acquisition of anisotropic 3-D MR images. Enhancing image resolution is desired but has been very challenging in medical image processing. Super resolution reconstruction based on sparse representation and overcomplete dictionary has been lately employed to address this problem; however, these methods require extra training sets, which may not be always available. This paper proposes a novel single anisotropic 3-D MR image upsampling method via sparse representation and overcomplete dictionary that is trained from in-plane high resolution slices to upsample in the out-of-plane dimensions. The proposed method, therefore, does not require extra training sets. Abundant experiments, conducted on simulated and clinical brain MR images, show that the proposed method is more accurate than classical interpolation. When compared to a recent upsampling method based on the nonlocal means approach, the proposed method did not show improved results at low upsampling factors with simulated images, but generated comparable results with much better computational efficiency in clinical cases. Therefore, the proposed approach can be efficiently implemented and routinely used to upsample MR images in the out-of-planes views for radiologic assessment and postacquisition processing.

This work proposes a novel approach for motion-robust diffusion-weighted (DW) brain MRI reconstruction through tracking temporal head motion using slice-to-volume registration. The slice-level motion is estimated through a filtering approach that allows tracking the head motion during the scan and correcting for out-of-plane inconsistency in the acquired images. Diffusion-sensitized image slices are registered to a base volume sequentially over time in the acquisition order where an outlier-robust Kalman filter, coupled with slice-to-volume registration, estimates head motion parameters. Diffusion gradient directions are corrected for the aligned DWI slices based on the computed rotation parameters and the diffusion tensors are directly estimated from the corrected data at each voxel using weighted linear least squares. The method was evaluated in DWI scans of adult volunteers who deliberately moved during scans as well as clinical DWI of 28 neonates and children with different types of motion. Experimental results showed marked improvements in DWI reconstruction using the proposed method compared to the state-of-the-art DWI analysis based on volume-to-volume registration. This approach can be readily used to retrieve information from motion-corrupted DW imaging data.

Fast magnetic resonance imaging slice acquisition techniques such as single shot fast spin echo are routinely used in the presence of uncontrollable motion. These techniques are widely used for fetal magnetic resonance imaging (MRI) and MRI of moving subjects and organs. Although high-quality slices are frequently acquired by these techniques, inter-slice motion leads to severe motion artifacts that are apparent in out-of-plane views. Slice sequential acquisitions do not enable 3-D volume representation. In this study, we have developed a novel technique based on a slice acquisition model, which enables the reconstruction of a volumetric image from multiple-scan slice acquisitions. The super-resolution volume reconstruction is formulated as an inverse problem of finding the underlying structure generating the acquired slices. We have developed a robust M-estimation solution which minimizes a robust error norm function between the model-generated slices and the acquired slices. The accuracy and robustness of this novel technique has been quantitatively assessed through simulations with digital brain phantom images as well as high-resolution newborn images. We also report here successful application of our new technique for the reconstruction of volumetric fetal brain MRI from clinically acquired data.

The accuracy and computational complexity of mutual information (MI) estimation are critical factors in multi-modality non-rigid image registration. This paper discusses the accuracy and complexity of MI estimation approaches based on non-rigid registration functions. General formulations have been derived for Shannon's and Renyi's definitions of MI, as well as Cauchy- Schwartz quadratic MI. The results obtained indicate that a fuzzy histogram binning estimation approach is significantly faster and more accurate than the conventional non-parametric Parzen window estimation approach. The analytical formulations obtained for various MI definitions are continuously differentiable and are shown to be computationally efficient for high-dimensional optimization problems particularly for non-rigid image registration.

This paper presents the use of Kullback-Leibler Distance (KLD) as part of an optimization framework to incorporate prior knowledge from field maps into non-rigid registration of echo-planar (EPI) to structural magnetic resonance brain images. An analytical expression is derived for the derivatives of KLD with respect to registration transformation parameters, which is shown to be computationally more efficient as compared to the derivatives of mutual information. Quantitative gold standard validation is carried out on simulated digital brain phantom images with synthesized deformations. In addition, in-vivo validation is performed via a cross-comparison of the similarity of high-resolution and low-resolution EPI to T1-and T2-weighted structural images. The results obtained indicate that the developed KLD-based non-rigid registration technique provides an effective way of correcting local distortions in echo-planar imaging.

Functional localization is a concept which involves the application of a sequence of geometrical and statistical image processing operations in order to define the location of brain activity or to produce functional/parametric maps with respect to the brain structure or anatomy. Considering that functional brain images do not normally convey detailed structural information and, thus, do not present an anatomically specific localization of functional activity, various image registration techniques are introduced in the literature for the purpose of mapping functional activity into an anatomical image or a brain atlas. The problems addressed by these techniques differ depending on the application and the type of analysis, i.e., single-subject versus group analysis. Functional to anatomical brain image registration is the core part of functional localization in most applications and is accompanied by intersubject and subject-to-atlas registration for group analysis studies. Cortical surface registration and automatic brain labeling are some of the other tools towards establishing a fully automatic functional localization procedure. While several previous survey papers have reviewed and classified general-purpose medical image registration techniques, this paper provides an overview of brain functional localization along with a survey and classification of the image registration techniques related to this problem.

Functional to anatomical brain image registration is needed for accurate localization of brain activation maps. Due to the presence of nonlinear distortions, it is more effective to consider non-rigid transformations to achieve such a registration. In this paper, a non-rigid registration technique based on the B-spline free-form deformation model and mutual information similarity measure is introduced. An optimization formulation is devised to achieve a fast and robust registration. This formulation differs from the previous formulations by utilizing a limited-memory, second-order optimization algorithm instead of the usual first-order gradient-based algorithms. It also enforces hard parameter constraints instead of constraints based upon physics or Jacobian smoothness. The results obtained indicate that this registration technique provides improvements over rigid and affine techniques when registering functional to anatomical magnetic resonance brain images.